Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    coverage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     males
    -0.08
    (LayoutInflater
    -0.07
    …”
    -0.07
     Parks
    -0.07
    (home
    -0.06
    .Names
    -0.06
     Institut
    -0.06
    ischen
    -0.06
     wik
    -0.06
     Arnold
    -0.06
    POSITIVE LOGITS
     SENSOR
    0.07
     intuitive
    0.07
     publicity
    0.07
    daq
    0.07
     Eg
    0.06
    ์กร
    0.06
     Strat
    0.06
    _filepath
    0.06
     сф
    0.06
     rested
    0.06
    Act Density 0.011%

    No Known Activations